Software Engineer β’ Embedded Systems β’ Data Engineering β’ Agentic AI
I'm an Electrical Engineer with a background in embedded software and the e-mobility industry. As an Application Engineer, I developed device drivers, built battery testing and automation systems, and worked on software for embedded platforms.
Today, my work is centered around software, data, and AI. I'm building projects in Data Engineering, Agentic AI, and modern backend systems while creating technical content and courses that document what I learn along the way.
I enjoy designing reliable, scalable systems from data pipelines and cloud-native applications to LLM-powered workflows and autonomous AI agents. My goal is to build practical software that bridges traditional engineering with modern AI.
-
Agentic AI & AI Agents
-
Applied Machine Learning
-
Data Engineering
-
Backend Engineering
-
Cloud & Distributed Systems
-
MLOps & LLMOps
-
Open Source & Developer Tools
- Developed full-stack applications and Data science / ML-based projects, demonstrating proficiency across both software engineering and data infrastructure layers.
My experience in embedded systems taught me to build reliable, data-centric automation in distributed environments :β skills that map directly to modern data engineering and cloud computing.
-
focus
Transitioning to working with production-grade data engineering, data science, and applied ML projects. -
skills
AWS Cloud Solutions: Glue, Lambda, API Gateway, S3, IaC (Terraform, CloudFormation), Simple Data Lake, CloudWatch, Cost Explorer, RDS, DynamoDB, IAM, VPC Security, Databricks, Jenkins (CI/CD), Airflow (DAGs). -
technical
AWS (Cloud): Lambda, S3, API Gateway, RDS, DynamoDB, IAM, Service Catalog, Terraform (IaC), CloudWatch, Cost Explorer, EKS, SQS, Glue, Athena, VPC, and others.Programming & Tools: Python, SQL, Unix Shell Scripting, PySpark, ETL.
DevOps & Automation: CI/CD, Git, Jenkins, Airflow, Terraform (IaC), Kafka (Basic), Containerisation (EKS, Docker).
Design & Architecture: System Design, Client-Server Architecture, Microservices, Serverless Architecture, Event-Driven Architecture, Data Modeling, Database Design.
Observability & Monitoring: OpenTelemetry (Otel), Jaeger, Databricks, Prometheus, Grafana, custom DIY Monitoring & Observability Panel.
Cloud-native streaming & batch pipelines for financial market data, data quality gates + real-time & analytical serving.
The Knowledge Drip
AI-driven knowledge delivery platform using hybrid search (BM25 + embeddings) & personalized insights via SMS.
RAG chatbot for Crime and Punishment β information retrieval + LLM via Streamlit.
Housing Price Prediction
Feature-engineered XGBoost pipeline; Streamlit app; Kaggle RMSE 0.12033.
SQL + Tableau dashboards on an artificial Brazil market dataset; structured insights & schema design.
Eniac Discount Analysis
Discount strategy & product segmentation on 7γγ«.8M revenue; seasonal demand & margin impact.
Minimalist JS + OpenWeather app with essentials + outfit suggestions.
Movie Night
CLI scraper curating top 50 films of 2023; filters + GCS/Heroku.
-
- Developing an Agentic AI solution as a freelance project for a startup, focusing on intelligent workflows, LLM orchestration, and production-ready AI system.
- Creating a project-based course on Agentic AI Systems and Data Engineering, covering practical architectures, tools, and real-world implementation.
-
- Agentic Knowledge Graph construction and graph-based reasoning for AI systems.
- Advanced Agentic AI architectures, LLMOps, and production deployment patterns.
Moving closer to downstream data roles through projects, certifications, and writing:
-
- Data Engineering β DeepLearning.AI (4-course specialization using AWS)
- Data Science β WBS Academy, Berlin
- Deep Learning β DeepLearning.AI (5-course specialization)
- RAG β DeepLearning.AI
- Building AI Agents and Agentic Workflows
- Docker & Kubernetes
- Short courses: GCP Essential Training; Statistics (3-part series)
-
- The Knowledge Drip
- The Complete Guide to RAG: Part I β Operational Mechanics
- The Complete Guide to RAG: Part II β Application Mechanics
- Understanding Deep Neural Networks β Foundations & Intuition (1a)
- Neural Network Mechanics (1b)
- Specifics of Deep Neural Nets & Bottlenecks (1c)
- Demystifying Word Embeddings: Neural Nets β Contrastive Learning
-
collaborate
Open to collaborating on projects involving Agentic AI, Data Engineering, Backend Systems, and Applied Machine Learning. -
askme
AI agents, LLM applications, data pipelines, backend engineering, embedded software, and building production-ready software systems.